{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "hendrycksTest-anatomy": { "acc": 0.32592592592592595, "acc_stderr": 0.040491220417025055, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.040491220417025055 }, "hendrycksTest-astronomy": { "acc": 0.2565789473684211, "acc_stderr": 0.03554180368025689, "acc_norm": 0.2565789473684211, "acc_norm_stderr": 0.03554180368025689 }, "hendrycksTest-business_ethics": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-clinical_knowledge": { "acc": 0.2528301886792453, "acc_stderr": 0.026749899771241235, "acc_norm": 0.2528301886792453, "acc_norm_stderr": 0.026749899771241235 }, "hendrycksTest-college_biology": { "acc": 0.3263888888888889, "acc_stderr": 0.03921067198982266, "acc_norm": 0.3263888888888889, "acc_norm_stderr": 0.03921067198982266 }, "hendrycksTest-college_chemistry": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "hendrycksTest-college_computer_science": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "hendrycksTest-college_mathematics": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-college_medicine": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "hendrycksTest-college_physics": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "hendrycksTest-computer_security": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "hendrycksTest-conceptual_physics": { "acc": 0.28936170212765955, "acc_stderr": 0.02964400657700962, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.02964400657700962 }, "hendrycksTest-econometrics": { "acc": 0.2894736842105263, "acc_stderr": 0.042663394431593935, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.042663394431593935 }, "hendrycksTest-electrical_engineering": { "acc": 0.2896551724137931, "acc_stderr": 0.037800192304380135, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.037800192304380135 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2777777777777778, "acc_stderr": 0.02306818884826111, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.02306818884826111 }, "hendrycksTest-formal_logic": { "acc": 0.3333333333333333, "acc_stderr": 0.042163702135578345, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.042163702135578345 }, "hendrycksTest-global_facts": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-high_school_biology": { "acc": 0.26129032258064516, "acc_stderr": 0.024993053397764822, "acc_norm": 0.26129032258064516, "acc_norm_stderr": 0.024993053397764822 }, "hendrycksTest-high_school_chemistry": { "acc": 0.23645320197044334, "acc_stderr": 0.029896114291733552, "acc_norm": 0.23645320197044334, "acc_norm_stderr": 0.029896114291733552 }, "hendrycksTest-high_school_computer_science": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "hendrycksTest-high_school_european_history": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "hendrycksTest-high_school_geography": { "acc": 0.21212121212121213, "acc_stderr": 0.029126522834586818, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.029126522834586818 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.24870466321243523, "acc_stderr": 0.031195840877700314, "acc_norm": 0.24870466321243523, "acc_norm_stderr": 0.031195840877700314 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.2358974358974359, "acc_stderr": 0.02152596540740873, "acc_norm": 0.2358974358974359, "acc_norm_stderr": 0.02152596540740873 }, "hendrycksTest-high_school_mathematics": { "acc": 0.22962962962962963, "acc_stderr": 0.02564410863926764, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.02564410863926764 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.2647058823529412, "acc_stderr": 0.02865749128507196, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.02865749128507196 }, "hendrycksTest-high_school_physics": { "acc": 0.2847682119205298, "acc_stderr": 0.03684881521389023, "acc_norm": 0.2847682119205298, "acc_norm_stderr": 0.03684881521389023 }, "hendrycksTest-high_school_psychology": { "acc": 0.26605504587155965, "acc_stderr": 0.01894602232222559, "acc_norm": 0.26605504587155965, "acc_norm_stderr": 0.01894602232222559 }, "hendrycksTest-high_school_statistics": { "acc": 0.2916666666666667, "acc_stderr": 0.030998666304560524, "acc_norm": 0.2916666666666667, "acc_norm_stderr": 0.030998666304560524 }, "hendrycksTest-high_school_us_history": { "acc": 0.27450980392156865, "acc_stderr": 0.03132179803083291, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.03132179803083291 }, "hendrycksTest-high_school_world_history": { "acc": 0.2869198312236287, "acc_stderr": 0.029443773022594693, "acc_norm": 0.2869198312236287, "acc_norm_stderr": 0.029443773022594693 }, "hendrycksTest-human_aging": { "acc": 0.28699551569506726, "acc_stderr": 0.03036037971029195, "acc_norm": 0.28699551569506726, "acc_norm_stderr": 0.03036037971029195 }, "hendrycksTest-human_sexuality": { "acc": 0.32061068702290074, "acc_stderr": 0.040933292298342784, "acc_norm": 0.32061068702290074, "acc_norm_stderr": 0.040933292298342784 }, "hendrycksTest-international_law": { "acc": 0.32231404958677684, "acc_stderr": 0.04266416363352167, "acc_norm": 0.32231404958677684, "acc_norm_stderr": 0.04266416363352167 }, "hendrycksTest-jurisprudence": { "acc": 0.3333333333333333, "acc_stderr": 0.04557239513497752, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04557239513497752 }, "hendrycksTest-logical_fallacies": { "acc": 0.22699386503067484, "acc_stderr": 0.032910995786157686, "acc_norm": 0.22699386503067484, "acc_norm_stderr": 0.032910995786157686 }, "hendrycksTest-machine_learning": { "acc": 0.2857142857142857, "acc_stderr": 0.04287858751340455, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04287858751340455 }, "hendrycksTest-management": { "acc": 0.14563106796116504, "acc_stderr": 0.0349260647662379, "acc_norm": 0.14563106796116504, "acc_norm_stderr": 0.0349260647662379 }, "hendrycksTest-marketing": { "acc": 0.3076923076923077, "acc_stderr": 0.030236389942173106, "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.030236389942173106 }, "hendrycksTest-medical_genetics": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "hendrycksTest-miscellaneous": { "acc": 0.30140485312899107, "acc_stderr": 0.01640909109726878, "acc_norm": 0.30140485312899107, "acc_norm_stderr": 0.01640909109726878 }, "hendrycksTest-moral_disputes": { "acc": 0.2976878612716763, "acc_stderr": 0.024617055388677003, "acc_norm": 0.2976878612716763, "acc_norm_stderr": 0.024617055388677003 }, "hendrycksTest-moral_scenarios": { "acc": 0.25251396648044694, "acc_stderr": 0.014530330201468636, "acc_norm": 0.25251396648044694, "acc_norm_stderr": 0.014530330201468636 }, "hendrycksTest-nutrition": { "acc": 0.28104575163398693, "acc_stderr": 0.025738854797818716, "acc_norm": 0.28104575163398693, "acc_norm_stderr": 0.025738854797818716 }, "hendrycksTest-philosophy": { "acc": 0.3440514469453376, "acc_stderr": 0.026981478043648047, "acc_norm": 0.3440514469453376, "acc_norm_stderr": 0.026981478043648047 }, "hendrycksTest-prehistory": { "acc": 0.31790123456790126, "acc_stderr": 0.025910063528240868, "acc_norm": 0.31790123456790126, "acc_norm_stderr": 0.025910063528240868 }, "hendrycksTest-professional_accounting": { "acc": 0.2907801418439716, "acc_stderr": 0.027090664368353178, "acc_norm": 0.2907801418439716, "acc_norm_stderr": 0.027090664368353178 }, "hendrycksTest-professional_law": { "acc": 0.26988265971316816, "acc_stderr": 0.011337381084250394, "acc_norm": 0.26988265971316816, "acc_norm_stderr": 0.011337381084250394 }, "hendrycksTest-professional_medicine": { "acc": 0.1801470588235294, "acc_stderr": 0.023345163616544855, "acc_norm": 0.1801470588235294, "acc_norm_stderr": 0.023345163616544855 }, "hendrycksTest-professional_psychology": { "acc": 0.3022875816993464, "acc_stderr": 0.018579232711113884, "acc_norm": 0.3022875816993464, "acc_norm_stderr": 0.018579232711113884 }, "hendrycksTest-public_relations": { "acc": 0.32727272727272727, "acc_stderr": 0.04494290866252089, "acc_norm": 0.32727272727272727, "acc_norm_stderr": 0.04494290866252089 }, "hendrycksTest-security_studies": { "acc": 0.2163265306122449, "acc_stderr": 0.02635891633490403, "acc_norm": 0.2163265306122449, "acc_norm_stderr": 0.02635891633490403 }, "hendrycksTest-sociology": { "acc": 0.24378109452736318, "acc_stderr": 0.030360490154014666, "acc_norm": 0.24378109452736318, "acc_norm_stderr": 0.030360490154014666 }, "hendrycksTest-us_foreign_policy": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-virology": { "acc": 0.28313253012048195, "acc_stderr": 0.03507295431370518, "acc_norm": 0.28313253012048195, "acc_norm_stderr": 0.03507295431370518 }, "hendrycksTest-world_religions": { "acc": 0.3508771929824561, "acc_stderr": 0.036602988340491624, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.036602988340491624 } }, "versions": { "hendrycksTest-abstract_algebra": 1, "hendrycksTest-anatomy": 1, "hendrycksTest-astronomy": 1, "hendrycksTest-business_ethics": 1, "hendrycksTest-clinical_knowledge": 1, "hendrycksTest-college_biology": 1, "hendrycksTest-college_chemistry": 1, "hendrycksTest-college_computer_science": 1, "hendrycksTest-college_mathematics": 1, "hendrycksTest-college_medicine": 1, "hendrycksTest-college_physics": 1, "hendrycksTest-computer_security": 1, "hendrycksTest-conceptual_physics": 1, "hendrycksTest-econometrics": 1, "hendrycksTest-electrical_engineering": 1, "hendrycksTest-elementary_mathematics": 1, "hendrycksTest-formal_logic": 1, "hendrycksTest-global_facts": 1, "hendrycksTest-high_school_biology": 1, "hendrycksTest-high_school_chemistry": 1, "hendrycksTest-high_school_computer_science": 1, "hendrycksTest-high_school_european_history": 1, "hendrycksTest-high_school_geography": 1, "hendrycksTest-high_school_government_and_politics": 1, "hendrycksTest-high_school_macroeconomics": 1, "hendrycksTest-high_school_mathematics": 1, "hendrycksTest-high_school_microeconomics": 1, "hendrycksTest-high_school_physics": 1, "hendrycksTest-high_school_psychology": 1, "hendrycksTest-high_school_statistics": 1, "hendrycksTest-high_school_us_history": 1, "hendrycksTest-high_school_world_history": 1, "hendrycksTest-human_aging": 1, "hendrycksTest-human_sexuality": 1, "hendrycksTest-international_law": 1, "hendrycksTest-jurisprudence": 1, "hendrycksTest-logical_fallacies": 1, "hendrycksTest-machine_learning": 1, "hendrycksTest-management": 1, "hendrycksTest-marketing": 1, "hendrycksTest-medical_genetics": 1, "hendrycksTest-miscellaneous": 1, "hendrycksTest-moral_disputes": 1, "hendrycksTest-moral_scenarios": 1, "hendrycksTest-nutrition": 1, "hendrycksTest-philosophy": 1, "hendrycksTest-prehistory": 1, "hendrycksTest-professional_accounting": 1, "hendrycksTest-professional_law": 1, "hendrycksTest-professional_medicine": 1, "hendrycksTest-professional_psychology": 1, "hendrycksTest-public_relations": 1, "hendrycksTest-security_studies": 1, "hendrycksTest-sociology": 1, "hendrycksTest-us_foreign_policy": 1, "hendrycksTest-virology": 1, "hendrycksTest-world_religions": 1 }, "config": { "model": "hf-causal", "model_args": "pretrained=workdir_7b/ckpt_355", "num_fewshot": 5, "batch_size": "8", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }